DEV Community: Mohammed Usama

How SOAP, DAP and BIRP notes differ, and when each one fits a vet visit

Mohammed Usama — Thu, 05 Nov 2026 17:00:02 +0000

SOAP, DAP, and BIRP organize the same visit three different ways. They are not interchangeable.

SOAP stands for Subjective, Objective, Assessment, Plan. Dr. Lawrence Weed built it for human medicine in the 1960s, and veterinary medicine adopted it as the standard note for an exam visit: what the owner reports, what you measure, your read on it, what happens next.

DAP stands for Data, Assessment, Plan. It comes from counseling and behavioral health, where one Data section replaces SOAP's separate Subjective and Objective sections. That makes it faster to write. In our opinion it suits a short recheck or a progress note.

BIRP stands for Behavior, Intervention, Response, Plan. It also comes from behavioral health. It tracks the presenting behavior, what was done about it, how the patient responded, and the plan. In our view, that fits a behavior consult better than an exam note does.

None of the guides we checked point to a required format for any of these. Pick the format that fits the visit in front of you.

We built our scribe to draft in all three, so changing the format is a setting and needs no rewrite.

Which format does your practice default to for everything, even visits it does not quite fit?

We make Perch, a dictation tool for veterinary clinics. It drafts the note while the vet talks, and when it cannot match a drug name to a known term it leaves the line for the vet instead of guessing. You can try it without an account at perchscribe.com/demo.

Sources: SOAP and the problem oriented medical record (Lawrence Weed, 1960s); DAP and BIRP definitions from clinical documentation guides (ICANotes on DAP, SimplePractice on BIRP).

Who is responsible for a veterinary note that AI drafted

Mohammed Usama — Mon, 02 Nov 2026 17:01:26 +0000

The AAVSB put it in writing in March 2025: when AI drafts the note, responsibility does not move to the software. It stays with the veterinarian who signs.

Their whitepaper says "the responsibility for appropriate use of AI rests entirely with the Licensee." On records specifically: the veterinarian "remains solely responsible for finalizing the medical record," and must "thoroughly review all AI-generated records to ensure their accuracy," since AI "may fabricate inaccurate content."

That is the case for reading before you sign, every time. Check each drug name against what was actually said, since a name that sounds close can still be the wrong drug. Check doses and routes against the dictation. Check that the vitals made it into the note, because they go missing when someone types them into the practice software instead of saying them. Check who said each thing, since a client's description is not a clinical finding. And take out anything that was never said in the exam before it reaches the chart.

What does "read before you sign" actually look like at your clinic?

Source: AAVSB, "Regulatory Considerations of the Use of Artificial Intelligence in Veterinary Medicine," March 2025.

Perch Essential costs $20 a month for the whole clinic

Mohammed Usama — Thu, 29 Oct 2026 17:00:03 +0000

A clinic with one, two or three vets should not have to price a scribe per doctor. Starting today, Perch has an Essential plan: $20 a month, one flat price for the whole clinic, for up to 3 vets.

What you get

Talk through the exam the way you already do. The words appear on screen while you are still speaking.
The note drafts itself in SOAP, DAP or BIRP. Read it, change anything, and sign.
Paste the finished note into your practice software. Perch runs in the browser on a phone or a desktop, with nothing to set up or install.
If a drug name can't be matched to a known term, Perch leaves it out of the note instead of guessing. Perch leaves the line for you to fill in, since a blank gets checked and a guess gets signed.
Your audio builds the transcript live and is gone afterward. It is not stored.

How to start

Every clinic gets 30 days of full access free, and you add a card only if you keep it. Sign up at perchscribe.com and talk through a real exam on your next visit. After the 30 days, Essential is $20 a month for the clinic, and nothing is charged until you add a card.

Clinics with more than 3 vets are on Standard: $149 a month covers 3 vets, and each vet after that is $49 a month. Every plan is on the pricing page.

Originally published at perch.talcoe.com/news/essential-plan.

Perch publishes three open releases for checking drug names in dictation

Mohammed Usama — Mon, 26 Oct 2026 17:00:02 +0000

Today we are publishing three open releases: a tool that checks a drug list against the audio of a dictation, a table of how veterinary drug names are said and misheard, and six blind dictation corpora.

The phoneme lane

The phoneme lane scores the audio, not the transcript. It runs a phoneme model over a dictation and scores every name on a formulary, a clinic's drug list, against the sounds it heard. It returns the best fits and the seconds of the clip where they sit. On clip r001 in blind6, read by the voice am_echo, the transcript spells famotidine "famitidine," maropitant "meripitin" and Entyce "Entice." The lane's four best fits are famotidine, morphine, Entyce and maropitant, and all four were said. In a Hindi sample sentence naming Heartgard and Bravecto, the transcript came out entirely in Devanagari, so a text matcher had no Latin letters to read. The lane ranked Heartgard first. It proposes names. It does not chart them.

Vet drug pronunciations

Vet drug pronunciations lists 265 drug and brand names used in veterinary practice, each with its pronunciation in IPA, the International Phonetic Alphabet, for American, British and South Asian English speakers. Sixty six of the names are on Perch's default list. For 59 of those the garble atlas lists the wrong words speech recognizers wrote when Kokoro voices said the name. Each is counted, and flagged if it is an ordinary English word. Atenolol, for example, came out as "8 nilal."

Blind dictation corpora

Perch blind dictation corpora are six sets of 70 rows, each a dictation or a trap, each written by an author who never saw Perch's matching code. In every set 45 are dictations and 25 are traps, sentences built to bait a system into offering a drug nobody said. Three Kokoro voices read each of the 420 rows, which makes 1,260 clips and about five hours of audio. The first set, blind1, holds the 70 clips of the trap set and adds two more voices for each sentence.

Why Perch publishes its tests

A company's own results are a claim until someone else can rerun them. The trap set post set the pattern: publish the clips and the scoring rule so anyone can check the work. These releases do the same with the sentences we score Perch on, the table our matcher reads when a name comes out garbled, and the lane we built for the names the matcher still missed.

Method notes

The phoneme model is wav2vec2 xlsr 53 espeak, with 388 phone symbols and 20 millisecond frames.
Every transcript quoted is Whisper large v3. The atlas holds what Whisper large v3 and MedASR wrote when six Kokoro voices said each of the 66 names in three sentence frames.
The pronunciations are espeak IPA for American and British English, plus three spoken forms per name from a language model, one each for American, British and South Asian English.

Where to find them

Phoneme lane, code under Apache 2.0: GitHub. DOI pending.
Vet drug pronunciations, data under CC BY 4.0: GitHub and Hugging Face. DOI pending.
Blind dictation corpora, data under CC BY 4.0: GitHub and Hugging Face. DOI pending.

Kokoro v1.0, from hexgrad and under Apache 2.0, voiced the clips. Run your own system against these sets, and open an issue on any of the repositories with what it misses. Perch is at perch.talcoe.com.

Originally published at perch.talcoe.com/news/three-open-releases.

Relief vets use Perch free, for good

Mohammed Usama — Sat, 24 Oct 2026 02:42:01 +0000

Relief vets walk into a different clinic, and a different practice system, almost every week, and still owe the same finished chart by the end of the shift. Perch runs in the browser, so it works the same way in every one of those rooms.

Starting today, relief veterinarians use Perch free, for good. There is no card, no clinic sponsor and no end date. If you work shifts at more than one clinic, through an agency, a marketplace or on your own, this is for you.

How it works

Start at perch.talcoe.com/relief and create your account. Perch asks you once to confirm that you work relief.
Each clinic you work is its own workspace. Switch between them in Settings, and your records stay with the clinic you charted for.
Perch drafts the note while you talk. Nothing enters the record until you review and sign it.

What is included

The whole product, not a trimmed tier: dictation on every visit, the running note in SOAP, DAP or BIRP, note history, and client discharge emails.

The first cohort

National Veterinary Technician Week runs October 18 to 24. If relief vets have signed notes with Perch by then, that week we will name the first relief cohort and say how many. Join before then to be counted in it: perch.talcoe.com/relief.

Originally published at perch.talcoe.com/news/relief-vets-free-forever.

Perch's Blind 70 Clip Drug Name Test

Mohammed Usama — Tue, 20 Oct 2026 03:15:00 +0000

Perch ran a blind 70 clip test built to catch invented medications, against a commercial veterinary AI scribe and against itself, with every miss on both sides published in the open.

Drafted with AI assistance from our test records. Every result below is in the public ledger linked at the end.

The failure mode

An AI scribe that turns a spoken exam into a written chart usually runs two steps in sequence. First a speech recognition layer turns audio into text. Second a language model layer reads that text and writes the structured note: the SOAP, the DAP, the medication list.

The first step is weak on its own. Drug names are unusual words, said quickly, often as a brand name next to its own generic in the same breath. Raw speech recognition misses a meaningful share of them.

The second step is where the real work happens, and where the real risk starts. A language model reading a rough transcript can recover a drug name the recognizer garbled, by matching it against context, such as the dose and the species. That is genuinely useful work. It is also the same mechanism that can produce a drug name nobody said. A model able to infer the right drug from a mangled word can just as easily infer a wrong one that merely sounds plausible, because the same inference step produces both outcomes.

We built a test set to find out whether this happens: on our own scribe, Perch, and on a commercial veterinary AI scribe already in clinical use. We are publishing what we found on both sides, at the same weight.

How the test set was built

Perch built the set as 70 short clips: 45 ordinary dictations that mirror how a vet talks through a visit, and 25 traps built to bait a scribe into charting a drug that was never said. A trap might be an offhand phone note that happens to contain a word that sounds like a brand name, with no clinical content in it at all.

The clips were written by someone who never saw the matching code on either side, so nothing in the corpus was tuned to pass. Each clip was rendered once, with a synthetic voice, so no clip has more than one reading.

We ran both products against the same 70 clips. We ran the commercial scribe the way any customer would run it, and scored Perch on the same clips through its own production pipeline.

Scoring rules

Both products are scored the same way. A drug actually said in a dictation counts as recalled if it appears correctly in the output text, or is charted in the note. A false offer is a drug name that ends up charted or offered in the note when the clinician never said it. There is no partial credit and no benefit of the doubt for either side.

The 45 dictation clips carried 84 drug mentions between them. That is the base every clip level result in this piece is measured against.

What happened on the run

Every example below comes from a clip read by a synthetic voice, not a real clinician, in a test we ran and scored ourselves. Real speech runs harder than a synthetic voice does. This is a reproducible shared test set, not an accuracy claim about either product.

One dictation read: "Started on Baytril, enrofloxacin, 5 mg per kg IV once," a brand name followed by its own generic, said together the way vets often say it to keep a record unambiguous. The commercial scribe's transcript rendered this as "batril and roflexacin." Its note generation step then charted both as separate medications: Baytril, and Roflexacin. Roflexacin does not exist. The chart, as generated, doubled the antibiotic dose under a name that is not a real drug. Perch, scored on the same clip, charted enrofloxacin and missed the Baytril brand, in both of its configurations: a miss, but no second drug.

A trap clip carried a different shape of risk. The dictation was an offhand phone note about "the next guard shift schedule change," nothing clinical. The same product's transcript wrote "the NexGard shift schedule change," and the brand name for a flea and tick product carried through into the note's narrative text, where no medication had been discussed at all.

Perch's own record is not clean either, and it belongs at the same weight as the two failures above. On a separate trap clip from Perch's own testing, a cat is described obliquely as being on Bexacat. An earlier build of Perch charted Zycortal, a real but wrong drug, from the garbled audio. The build running now declines to chart anything on that same clip. And one configuration we evaluated while building the current matcher, and never shipped, charted ProHeart from a misheard "pretreated"; this test set caught it before it reached a clinic. We name our own build and the fix here, and leave the comparison at that.

Credit belongs on the other side too. One dictation contained a badly garbled reading of atenolol, rendered by the recognition step as something close to "8 nilal." The commercial scribe's repair layer recovered the correct drug name from that garble. One of Perch's two configurations missed it on the same clip. That repair layer did real work across the run, recovering several other names a raw transcript alone would have lost.

The same repair layer, while recovering names, also quietly dropped the brand half of more than one dictated brand and generic pair: Apoquel twice, plus Clavamox, Rimadyl and Cerenia each lost their brand name in the finished note, leaving only the generic behind. Nobody flagged the loss, since the note read as complete either way. Perch, scored on those same five pairs, charted both halves of each. Its one dropped brand in the run was Baytril, on the clip above.

A few smaller errors from the same run are worth naming plainly. The commercial scribe's chart spelled a dictated Cosequin as "Kosquin," close enough to pass a quick read but wrong on the page. Entyce, an appetite stimulant, defeated every system in the test, Perch included, and the commercial scribe's note put the ordinary word "Entice" next to its medication list. On two other clips its note stated a diagnosis the clinician never dictated, and a surgery date nobody said, detail added on top of what was actually spoken.

Across the 25 trap clips, Perch charted nothing that was not said. The commercial scribe charted no drug from the ordinary word bait either. Its two trap misses were NexGard in the narrative and an unstated generic name, phenylpropanolamine, added next to a correctly charted Proin.

Why Perch refuses instead of guessing

Perch's rule for an unresolved drug name is to leave it out of the note rather than fill in a best guess. If the audio does not clearly match a known term, that line stays blank for the vet to fill in on review, rather than being written with a name that only sounds right.

A blank line gets checked before a note is signed. A wrong but plausible drug name can read as complete and get missed entirely. That asymmetry is the reason for the design. Across both of Perch's configurations in this run, the count of invented drug names charted was zero. The count of real drug names it declined to guess, and left blank instead, is a cost of the same design, accepted on purpose.

Limits

Every clip in this set is synthetic speech, generated by text to speech voices, one voice per clip. This is our own test, run and scored by the team that built Perch, not an outside body. We expect real clinician speech, with background noise and cross talk, to run harder for any scribe, ours included.

We ran the commercial scribe through its own documented upload flow, at its default settings, on a trial account, generating one note per case from its stock template, with no manual edits and no clinic drug list uploaded on either side. That is an out of box comparison, not a claim about what either product does once tuned for a specific clinic.

How to run this yourself

The clips, the written dictations, the scoring script, and the full ledger of what each product charted on every clip, including every miss on both sides, are published at https://github.com/perchvet/perch-trapset. The rule is the one described above: a drug counts as recalled if it appears or is charted, a false offer is anything charted that nobody said. Any scribe, including a future build of Perch, can be scored against the same 70 clips the same way.

Mohammed Usama is a cofounder of Talcoe LLC, which makes Perch, a veterinary AI scribe. Questions about the test set: mo@talcoe.com.